learning/prompts/code-generation/07_io_json.md

Prompt:
Write the Python code to read data from JSON files using Apache Beam.

Response:
Your Apache Beam pipeline can read data from [JSON files](https://www.json.org/) using the Apache Beam [TextIO connector](https://beam.apache.org/releases/pydoc/current/apache_beam.io.textio.html).

```python
import logging
import apache_beam as beam

from apache_beam import Map
from apache_beam.io.textio import ReadFromJson
from apache_beam.options.pipeline_options import PipelineOptions


class JsonOptions(PipelineOptions):
    @classmethod
    def _add_argparse_args(cls, parser):
        parser.add_argument(
            '--file_path',
            default="gs://your-bucket/your-file.json",
            help='Json file path'
        )


def run():
    """
    This pipeline reads from Json file defined by the --file_path argument.
    """

    options = JsonOptions()

    with beam.Pipeline(options=options) as p:

        output = p | "Read from Json file" >> ReadFromJson(
            path=options.file_path,
            lines=False
            )


if __name__ == "__main__":
    logging.getLogger().setLevel(logging.INFO)
    run()
```

The `JsonOptions` class is a custom class that extends the `PipelineOptions` object. This code uses [pipeline options](https://beam.apache.org/documentation/patterns/pipeline-options/) to parse command-line arguments.

The [`ReadFromJson`](https://beam.apache.org/releases/pydoc/current/apache_beam.io.textio.html#apache_beam.io.textio.ReadFromJson) transform is a built-in Apache Beam transform that reads data from a JSON file.